Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    made discoveries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     basi
    0.46
     organisms
    0.43
     OBS
    0.42
     pirm
    0.42
     ऑब्
    0.42
    grandfather
    0.40
    ூர்
    0.40
    DanhMucSP
    0.39
     Agricult
    0.39
    Cumm
    0.38
    POSITIVE LOGITS
     usher
    0.39
     Bağ
    0.38
     지속
    0.37
     آش
    0.37
    ausal
    0.37
     кино
    0.36
    일본
    0.36
    倪
    0.36
     disponíveis
    0.35
    Trust
    0.35
    Act Density 0.000%

    No Known Activations